Beyond Average Performance – exploring regions of deviating performance for black box classification models

09/16/2021
by   Luis Torgo, et al.
10

Machine learning models are becoming increasingly popular in different types of settings. This is mainly caused by their ability to achieve a level of predictive performance that is hard to match by human experts in this new era of big data. With this usage growth comes an increase of the requirements for accountability and understanding of the models' predictions. However, the degree of sophistication of the most successful models (e.g. ensembles, deep learning) is becoming a large obstacle to this endeavour as these models are essentially black boxes. In this paper we describe two general approaches that can be used to provide interpretable descriptions of the expected performance of any black box classification model. These approaches are of high practical relevance as they provide means to uncover and describe in an interpretable way situations where the models are expected to have a performance that deviates significantly from their average behaviour. This may be of critical relevance for applications where costly decisions are driven by the predictions of the models, as it can be used to warn end users against the usage of the models in some specific cases.

READ FULL TEXT

page 6

page 13

page 14

page 17

research
02/10/2020

Interpretable Companions for Black-Box Models

We present an interpretable companion model for any pre-trained black-bo...
research
06/23/2018

DALEX: explainers for complex predictive models

Predictive modeling is invaded by elastic, yet complex methods such as n...
research
09/05/2022

Visualization Of Class Activation Maps To Explain AI Classification Of Network Packet Captures

The classification of internet traffic has become increasingly important...
research
08/03/2017

A glass-box interactive machine learning approach for solving NP-hard problems with the human-in-the-loop

The goal of Machine Learning to automatically learn from data, extract k...
research
02/12/2021

Interpretable Predictive Maintenance for Hard Drives

Existing machine learning approaches for data-driven predictive maintena...
research
11/09/2022

Mapping the Ictal-Interictal-Injury Continuum Using Interpretable Machine Learning

IMPORTANCE: An interpretable machine learning model can provide faithful...
research
02/10/2022

Interpretable pipelines with evolutionarily optimized modules for RL tasks with visual inputs

The importance of explainability in AI has become a pressing concern, fo...

Please sign up or login with your details

Forgot password? Click here to reset